Commit graph

4763 commits

Author SHA1 Message Date
Matt Rubens
23bbad04e2
Update CHANGELOG.md 2025-06-13 23:40:44 -04:00
github-actions[bot]
879868448a changeset version bump 2025-06-14 03:36:03 +00:00
Matt Rubens
405ffacd04
v3.20.3 (#4685) 2025-06-13 23:35:29 -04:00
Matt Rubens
254baa8704
Fix errant maxReadFileLine default (#4683) 2025-06-13 23:30:28 -04:00
Matt Rubens
1a4c6892a3
Make listing tools respect auto-approve settings for outside of the workspace (#4682) 2025-06-13 23:12:31 -04:00
Matt Rubens
d67b351fca
Fix inconsistencies in markdown file i18n (#4681) 2025-06-13 23:05:25 -04:00
Matt Rubens
3937e06380
Update Indonesian locales/ files (#4680) 2025-06-13 22:46:28 -04:00
Daniel
91f632ed00
fix: improve prompt history navigation to not interfere with text editing (#4677) 2025-06-13 22:10:50 -04:00
Daniel
4ccd6fab2d
Update Indonesian locale files for chat and settings (#4675) 2025-06-13 20:47:14 -04:00
Christiaan Arnoldus
206c292498
feat: Indonesian translation (#4672)
* Copy Indonesian text files from Kilo Code

* Use Roo to update its own Indonesian translation
2025-06-13 20:25:05 -04:00
Daniel
feb2fa8443
Fix multi-file diff error handling and UI feedback (#4674)
fix: improve multi-file diff error handling and UI feedback

- Fix nested array issue in multi-file-search-replace strategy
- Consolidate diff error reporting to single message
- Fix infinite spinner on single file diff failures
2025-06-13 20:09:04 -04:00
John Richmond
7dd56d6551
Move marketplace types to @roo-code/types (#4671)
And do some cleanup & consolidation.
2025-06-13 17:02:16 -07:00
Matt Rubens
7d0b22f9e6
Add logic to prevent auto-approving edits of configuration files (#4667)
* Add logic to prevent auto-approving edits of configuration files

* Fix tests

* Update patterns
2025-06-13 19:58:55 -04:00
Matt Rubens
10b2fb32ed
Adjust searching outside of the workspace to respect the auto-approve… (#4670)
Adjust searching outside of the workspace to respect the auto-approve checkbox
2025-06-13 18:49:39 -04:00
Daniel
ec9b27d587
Resolve diff editor race condition in multi-monitor setups (#4578)
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Mnehmos <Mnehmos@gmail.com>
2025-06-13 16:54:14 -04:00
github-actions[bot]
c0876d0b56
Changeset version bump (#4663)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-06-13 15:17:57 -04:00
Matt Rubens
0284b1101c
v3.20.2 (#4662) 2025-06-13 15:13:15 -04:00
Matt Rubens
ca0338af15
Limit search_files to only look within the workspace (#4642) 2025-06-13 12:10:43 -04:00
Eamon Nerbonne
e535b55076
♻️ Refactor: Avoid type system duplication (#4596) 2025-06-13 12:10:34 -04:00
Sam Hoang Van
8fb368dd6b
feat(ui): add max height constraint to MCP execution response (#4644) 2025-06-13 11:29:41 -04:00
Hannes Rudolph
fc82485563
Docs extractor mode (#4621) 2025-06-13 11:29:12 -04:00
Daniel
a1b8b12928
Prevent MCP 'installed' label from being squeezed #4630 (#4649) 2025-06-13 11:28:33 -04:00
Daniel
48d0b19324
Feat: Improve Issue Fixer Rules for Targeted Fixes (#4652) 2025-06-13 11:28:05 -04:00
Daniel
87186067f9
Feat: Improve PR Reviewer Rules (#4651) 2025-06-13 11:08:51 -04:00
Daniel
28ad8d719e
Reapply reasoning for bedrock with fix (#4645)
* Add reasoning budget support to Bedrock models and update related components

- Introduced `supportsReasoningBudget` property in Bedrock models.
- Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads.
- Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support.
- Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`.
- Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`.

* Add BedrockThinkingConfig interface and update payload structure

* fix: address PR review feedback (#4481)

- Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported
- Break down complex thinking enabled condition with clear documentation
- Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events
- Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility

* feat: show ThinkingBudget component unconditionally

Remove selectedProviderModels.length check to display ThinkingBudget
for all providers, not just those with available models

---------

Co-authored-by: hannesrudolph <hrudolph@gmail.com>
2025-06-13 11:07:27 -04:00
Sam Hoang Van
9eb9fabee0
feat(ui): sync BatchDiffApproval styling with BatchFilePermission (#4640) 2025-06-13 09:01:47 -04:00
pugazhendhi-m
2cb02d6512
Add cache breakpoints for custom vertex models on Unbound (#4585)
Co-authored-by: Pugazhendhi <pugazhendhi@unboundsecurity.ai>
2025-06-13 08:29:40 -04:00
Raffael
dc00167289
Update ContextManagementSettings.tsx (#4634)
Allow 5% threshold for context condensing (thats already 50k with gemini 1M context, enough for many tasks)
2025-06-13 06:42:55 -04:00
Chris Estreich
28a16c9ee7
Force tar-fs >=2.1.3 (#4629) 2025-06-12 23:27:41 -07:00
github-actions[bot]
4e46698fd3
Changeset version bump (#4628)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-06-13 01:49:08 -04:00
Matt Rubens
9db7840655
v3.20.1 (#4627) 2025-06-13 01:46:22 -04:00
Matt Rubens
47e84b4572
Revert "feat: Add reasoning budget support to Bedrock models for extended thinking (#4201)" (#4626) 2025-06-13 01:43:06 -04:00
Hannes Rudolph
bde7a7bf2a
feat: Add indexing status badge to chat view (#4429) (#4532)
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
2025-06-12 21:56:57 -04:00
Daniel
5f29348519
Improve performance of MCP execution block (#4615) 2025-06-12 21:17:55 -04:00
github-actions[bot]
0cf3f00bab
Update contributors list (#4348)
docs: update contributors list [skip ci]

Co-authored-by: mrubens <2600+mrubens@users.noreply.github.com>
2025-06-12 20:57:45 -04:00
Matt Rubens
1492e5780e
Update CHANGELOG.md 2025-06-12 20:24:09 -04:00
github-actions[bot]
ca5f2d05f9
Changeset version bump (#4593)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-06-12 18:17:12 -04:00
Matt Rubens
ffc8dc7b6b
v3.20 (#4609)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-06-12 17:54:53 -04:00
Daniel
33ce5a2e24
Fix undefined on multi-file apply_diff output (#4608)
feat: enhance file handling in `apply_diff` case to support legacy and multi-file formats
2025-06-12 16:46:16 -04:00
Matt Rubens
184c4803c6
Move concurrent reads into context settings and default to 5 (#4597)
* Move concurrent reads into context settings and default to 5

* Spacing tweaks

* Change max back to 100
2025-06-12 16:21:39 -04:00
Matt Rubens
2eca105e35
Add a footer to the marketplace to report issues (#4604) 2025-06-12 16:18:07 -04:00
Chris Estreich
fe52c19fde
Evals fixes (#4599) 2025-06-12 13:01:59 -07:00
Trung Dang
84ccf3fcc3
feat: add injectVariables(), support magic variables for MCPs (workspaceFolder) (#4442)
* feat: add `injectVariables()`, support magic variables for MCPs

* fix: fallback for `workspaceFolder` should just be an empty string

Previously this is intended so that the CLI receives a correct empty path argument, but on a second thought, if the user have added the quotes themselves it might cause error.

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* chore: remove unused import

* chore: better log format

* chore: better describe the accepted config type and more extensive test

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-06-12 13:17:41 -04:00
Dixie Flatline
c481827cbb
Manually specify openai-compat format and parse it (#4463)
* Manually specify openai-compat format and parse it

* fixup! Manually specify openai-compat format and parse it

* Expect base64 in embedding test arguments

* fixup! Manually specify openai-compat format and parse it

Remove debug logs

* fixup! Manually specify openai-compat format and parse it

Improve comment

* fixup! Manually specify openai-compat format and parse it

* Add tests to exercise base64 decode of embeddings

* Add tests to verify openai base64 and brokenness behavior

* feat: improve typing

* refactor: switch from jest to vitest for mocking in tests

---------

Co-authored-by: Dixie Flatline <dflatline>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
2025-06-12 13:12:48 -04:00
axb
dfcf8fe760
add mermaid buttons (#4547)
* add mermaid buttons

* feat: Add Modal, TabButton, and ZoomControls components

* feat: Add error handling messages for image operations and file opening

* mermaid: Add drag functionality and support contious zooming

* add active color for tabbutton

* refactor zoom controls

* refactor: Remove unused svgToPng prop and simplify handleCopy function

* Move zoom to constants and increase max zoom

* feat: add save image functionality and refactor image handling

* feat: add translations

---------

Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-06-12 13:06:27 -04:00
Matt Rubens
85fd86e675
Revert "Always focus the panel when clicked to ensure menu buttons are visible" (#4592)
Revert "Always focus the panel when clicked to ensure menu buttons are visibl…"

This reverts commit 1b1e5a20f1.
2025-06-12 12:51:34 -04:00
Hannes Rudolph
fb3a728a30
feat: Add reasoning budget support to Bedrock models for extended thinking (#4201) (#4481)
* Add reasoning budget support to Bedrock models and update related components

- Introduced `supportsReasoningBudget` property in Bedrock models.
- Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads.
- Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support.
- Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`.
- Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`.

* Add BedrockThinkingConfig interface and update payload structure

* fix: address PR review feedback (#4481)

- Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported
- Break down complex thinking enabled condition with clear documentation
- Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events
- Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility
2025-06-12 12:39:21 -04:00
Sam Hoang Van
7bed94454a
feat: Enhance apply_diff with XML for multi-file/multi-diff operations & batch UI (#3342)
* feat: add BatchDiffApproval component for multi-file diff application

- Introduced a new component `BatchDiffApproval` to handle the approval of batch changes across multiple files.
- Integrated the `BatchDiffApproval` component into `ChatRow` to display batch diff requests.
- Updated experimental settings to include a toggle for multi-file apply diff functionality.
- Enhanced localization files to support new strings related to batch changes in multiple languages.
- Updated tests to cover the new multi-file apply diff feature.

* revert this

* fix: update applyDiff parameter type to accept string or DiffItem

* refactor: keep original file name for apply diff tool

* revert this

* Update src/core/webview/__tests__/ClineProvider.test.ts

* revert this

* fix: keep the original path if the experiment is disabled

* test: add dynamic strategy selection tests for MultiSearchReplaceDiffStrategy and MultiFileSearchReplaceDiffStrategy

* fix: mock applyDiffTool module and ensure legacy tool resolves successfully in tests

* remove this

* ellipsis suggestion

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* refactor: mirror concurrent file reads

---------

Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-06-12 12:36:34 -04:00
Edwin P Jacques
8b6f5f8baa
update xai models and pricing (#4315)
* update xai models and pricing

* cache accounting for xAI

* change log
2025-06-12 11:59:45 -04:00
Chris Estreich
15e3d6fc87
feat(tests): core tools integration tests (#4433)
* feat(tests): add apply_diff tool tests

* feat(tests): add tests for write_to_file tool functionality

* feat(tests): add comprehensive tests for read_file tool functionality

* feat(tests): add tests for execute_command tool functionality

* feat(integration-tester): add integration testing role with comprehensive guidelines

* feat(tests): enhance test runner with grep and specific file filtering

* feat(tests): add comprehensive tests for search_files tool functionality

* feat(tests): add comprehensive tests for list_files tool functionality

* feat(tests): add tests for insert_content tool functionality

* feat(tests): add comprehensive tests for search_and_replace tool functionality

* feat(tests): add comprehensive tests for use_mcp_tool functionality

* feat(tests): increase timeout values for various tool tests to improve reliability

* fix(tests): add non-null assertion for workspaceDir assignment in multiple test files

* feat(tests): enhance read_file tool tests with increased timeouts and improved prompts

* feat(tests): enhance read_file tool tests to extract and verify tool results

* feat(tests): enhance execute_command tool tests with additional context in prompts

* refactor(tests): remove script execution test and related setup for execute_command tool

* fix(tests): increase timeout for task start and completion in apply_diff and read_file tests

* fix(tests): clarify error handling message in command execution test

* refactor(tests): remove error handling test and related setup for execute_command tool

* fix: update openRouterModelId to use anthropic/claude-3.5-sonnet

* fix: update openRouterModelId to use openai/gpt-4.1

* fix(tests): increase timeouts for apply_diff, execute_command, and search_and_replace tests

* fix(tests): disable terminal shell integration for execute_command tool tests

* chore: rewrite integration tester mode

* Update .roo/rules-integration-tester/1_workflow.xml

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

---------

Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-06-12 11:50:25 -04:00